Granite 4.2 30B API PricingNEW
IBM · released 2026-08-25
Pricing
0.016¢ / 1K
0.065¢ / 1K
0.028¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0275¢ |
| RAG query | 4,000 in / 500 out | 0.0965¢ |
| Long document summary | 50,000 in / 1,000 out | 0.865¢ |
| Code review of a 2k-line file | 30,000 in / 2,000 out | 0.61¢ |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $8.25 |
Cost = (input tokens ÷ 1,000,000 × $0.16) + (output tokens ÷ 1,000,000 × $0.65).
Benchmarks
#177 of 533
#114 of 197
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Qwen3.5 4B (Reasoning) | 13.1 | $0.06 |
| Nemotron 3.5 Lightning | 12.9 | $0.095 |
| GPT-5 nano (high) | 13.0 | $0.138 |
| Step 3.5 Flash 2603 | 17.0 | $0.15 |
| Step 3.5 Flash | 16.6 | $0.15 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| GLM-4.6 (Non-reasoning) | 14.9 | $0.981 |
| GLM-4.7-Flash (Reasoning) | 14.9 | $0.153 |
| DeepSeek V3.1 Terminus (Reasoning) | 14.8 | $1.914 |
| Granite 4.2 30B | 14.8 | $0.282 |
| Grok 3 mini Reasoning (high) | 14.6 | $0.35 |
| DeepSeek V3.2 Speciale | 14.5 | — |
| Gemini 2.5 Pro Preview (May' 25) | 14.5 | $3.438 |
More from IBM
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Granite 4.2 8B | 11.1 | $0.107 |
| Granite 4.2 3B | 9.1 | $0.052 |
| Granite 4.1 30B | 7.4 | — |
| Granite 4.1 8B | 6.6 | $0.063 |
| Granite 4.0 H Small | 6.0 | $0.107 |
| Granite 4.1 3B | 5.9 | — |
| Granite 4.0 H 1B | 5.2 | — |
| Granite 4.0 Micro | 5.1 | — |
Count tokens & estimate cost for Granite 4.2 30B See Granite 4.2 30B on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops Granite 4.2 30B?
Granite 4.2 30B is developed by IBM, released 2026-08-25.
How much does Granite 4.2 30B cost per million tokens?
Granite 4.2 30B costs $0.16 per 1M input tokens and $0.65 per 1M output tokens ($0.282 blended), per Artificial Analysis's official pricing data.
How does Granite 4.2 30B rank on benchmarks?
Granite 4.2 30B scores 14.8 on the Artificial Analysis Intelligence Index, ranking #177 of 533 models we track.
Is there a cheaper model with similar intelligence to Granite 4.2 30B?
Yes — Qwen3.5 4B (Reasoning) scores similar intelligence (13.1) at $0.06/1M blended, versus $0.282/1M for Granite 4.2 30B.
Where does this data come from?
Pricing and benchmark data for Granite 4.2 30B comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.